Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 10094
    Prev
    Next
    INDEX
    Explanations

    references to objects, entities, or concepts that are distinct from a specific main object or entity

    oai_token-act-pair · gpt-3.5-turbo

    the recurring theme of "other" in relation to different contexts and categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hua
    -0.77
    hower
    -0.74
    uca
    -0.67
    zai
    -0.65
    hak
    -0.63
    uterte
    -0.63
    ettel
    -0.63
    vg
    -0.62
    onics
    -0.62
    atown
    -0.62
    POSITIVE LOGITS
    worldly
    1.04
     aspects
    0.93
     facets
    0.90
     components
    0.78
     respects
    0.75
     kinds
    0.74
     avenues
    0.74
     factions
    0.73
    iating
    0.73
     except
    0.71
    Activations Density 0.034%

    No Known Activations